KyutaiCASA
CASA Qwen 2.5 VL 3B
This adaptation changes Qwen 2.5 VL 3B Instruct from image-token insertion to cross-attention.
Research release
The architecture determines how images enter the model
CASA lets text attend to visual features without inserting every image token into the language sequence. The code supplies a custom architecture and processor; this is not an unchanged upstream Qwen or Helium checkpoint.CASA-Qwen2_5-VL-3B: Kyutai model card
Specifications & access
| Detail | Value and conditions |
|---|---|
| Status | Research release |
| Access | Downloadable |
| Model identifiers | kyutai/CASA-Qwen2_5-VL-3B |
| Weight license | CC BY-NC-SA 4.0.CASA-Qwen2_5-VL-3B: Kyutai model card |
| Upstream components | Qwen 2.5 VL 3B Instruct; its Qwen Research License also applies.CASA-Qwen2_5-VL-3B: Kyutai model card |
Related models
- Helium 1 VL 2B
Kyutai ยท CASA
An instruction-tuned vision-language reference model that inserts image tokens into the text sequence.
Launch date not confirmedResearch releaseDownloadable